Superpixel-Based PolSAR Images Change Detection

Previous polarimetric synthetic aperture radar (PolSAR) images change detection methods are generally undertaken in the pixel scale, resulting in overlooking the semantic information. To solve this problem, this paper presents a superpixel-based PolSAR images change detection methods. Different from some previous methods, an improved SLIC superpixel segmentation method is introduced in polarimetric interferometric SAR (Pol-InSAR) images processing, which can segment two PolSAR images simultaneously. Moreover, along with the difference maps (DMs) generated based on the complex wishart distribution and the total intensity, we also use color information to generate the DM between PolSAR images, which has long been overlooked in PolSAR images change detection. Based on the segmentation results and three DMs, two different change detection schemes are proposed. One is to perform the majority voting to three change detection results using the above mentioned DMs. Another is to fuse the three DMs and generate a refined DM, and the change detection is performed on the refined DM. Two Radarsat-2 images acquired over Suzhou city, China, are used in our experiments to validate the proposed methods, and the experimental results show that the proposed schemes can improve the change detection results significantly.